public abstract class StochasticPathwiseLevenbergMarquardtAD extends StochasticPathwiseLevenbergMarquardt
The design avoids the need to define the objective function as a separate class. The objective function is defined by overriding a class method, see the sample code below.
The Levenberg-Marquardt solver is implemented in using multi-threading.
The calculation of the derivatives (in case a specific implementation of
setDerivatives(RandomVariableInterface[] parameters, RandomVariableInterface[][] derivatives) is not
provided) may be performed in parallel by setting the parameter numberOfThreads.
To use the solver inherit from it and implement the objective function as
setValues(RandomVariableInterface[] parameters, RandomVariableInterface[] values) where values has
to be set to the value of the objective functions for the given parameters.
You may also provide an a derivative for your objective function by
additionally overriding the function setDerivatives(RandomVariableInterface[] parameters, RandomVariableInterface[][] derivatives),
otherwise the solver will calculate the derivative via finite differences.
To reject a point, it is allowed to set an element of values to Double.NaN
in the implementation of setValues(RandomVariableInterface[] parameters, RandomVariableInterface[] values).
Put differently: The solver handles NaN values in values as an error larger than
the current one (regardless of the current error) and rejects the point.
Note, however, that is is an error if the initial parameter guess results in an NaN value.
That is, the solver should be initialized with an initial parameter in an admissible region.
| 0.0 * x1 + 1.0 * x2 = 5.0 |
| 2.0 * x1 + 1.0 * x2 = 10.0 |
LevenbergMarquardt optimizer = new LevenbergMarquardt() {
// Override your objective function here
public void setValues(RandomVariableInterface[] parameters, RandomVariableInterface[] values) {
values[0] = parameters[0] * 0.0 + parameters[1];
values[1] = parameters[0] * 2.0 + parameters[1];
}
};
// Set solver parameters
optimizer.setInitialParameters(new RandomVariableInterface[] { 0, 0 });
optimizer.setWeights(new RandomVariableInterface[] { 1, 1 });
optimizer.setMaxIteration(100);
optimizer.setTargetValues(new RandomVariableInterface[] { 5, 10 });
optimizer.run();
RandomVariableInterface[] bestParameters = optimizer.getBestFitParameters();
See the example in the main method below.
The class can be initialized to use a multi-threaded valuation. If initialized
this way the implementation of setValues must be thread-safe.
The solver will evaluate the gradient of the value vector in parallel, i.e.,
use as many threads as the number of parameters.
StochasticOptimizerInterface.ObjectiveFunction| Constructor and Description |
|---|
StochasticPathwiseLevenbergMarquardtAD(List<RandomVariableInterface> initialParameters,
List<RandomVariableInterface> targetValues,
int maxIteration,
ExecutorService executorService) |
StochasticPathwiseLevenbergMarquardtAD(List<RandomVariableInterface> initialParameters,
List<RandomVariableInterface> targetValues,
int maxIteration,
int numberOfThreads) |
StochasticPathwiseLevenbergMarquardtAD(RandomVariableInterface[] initialParameters,
RandomVariableInterface[] targetValues,
int maxIteration,
int numberOfThreads) |
StochasticPathwiseLevenbergMarquardtAD(RandomVariableInterface[] initialParameters,
RandomVariableInterface[] targetValues,
RandomVariableInterface[] weights,
RandomVariableInterface[] parameterSteps,
int maxIteration,
RandomVariableInterface errorTolerance,
ExecutorService executorService) |
| Modifier and Type | Method and Description |
|---|---|
protected void |
prepareAndSetDerivatives(RandomVariableInterface[] parameters,
RandomVariableInterface[] values,
RandomVariableInterface[][] derivatives) |
protected void |
prepareAndSetValues(RandomVariableInterface[] parameters,
RandomVariableInterface[] values) |
clone, getBestFitParameters, getCloneWithModifiedTargetValues, getCloneWithModifiedTargetValues, getIterations, getLambda, getLambdaDivisor, getLambdaMultiplicator, getMeanSquaredError, getRootMeanSquaredError, main, run, setDerivatives, setErrorMeanSquaredCurrent, setLambda, setLambdaDivisor, setLambdaMultiplicator, setValuespublic StochasticPathwiseLevenbergMarquardtAD(List<RandomVariableInterface> initialParameters, List<RandomVariableInterface> targetValues, int maxIteration, ExecutorService executorService)
public StochasticPathwiseLevenbergMarquardtAD(List<RandomVariableInterface> initialParameters, List<RandomVariableInterface> targetValues, int maxIteration, int numberOfThreads)
public StochasticPathwiseLevenbergMarquardtAD(RandomVariableInterface[] initialParameters, RandomVariableInterface[] targetValues, int maxIteration, int numberOfThreads)
public StochasticPathwiseLevenbergMarquardtAD(RandomVariableInterface[] initialParameters, RandomVariableInterface[] targetValues, RandomVariableInterface[] weights, RandomVariableInterface[] parameterSteps, int maxIteration, RandomVariableInterface errorTolerance, ExecutorService executorService)
protected void prepareAndSetValues(RandomVariableInterface[] parameters, RandomVariableInterface[] values) throws SolverException
prepareAndSetValues in class StochasticPathwiseLevenbergMarquardtSolverExceptionprotected void prepareAndSetDerivatives(RandomVariableInterface[] parameters, RandomVariableInterface[] values, RandomVariableInterface[][] derivatives) throws SolverException
prepareAndSetDerivatives in class StochasticPathwiseLevenbergMarquardtSolverExceptionCopyright © 2018. All rights reserved.